WINETASTER ON 12/04/06 WITH 8 JUDGES AND 8 WINES BASED ON RANKS, IDENT=N Copyright (c) 1995-2006 Richard E. Quandt, V. 1.65
FLIGHT 1: Number of Judges = 8 Number of Wines = 8
Identification of the Wine: The judges' overall ranking:
Wine A is Ch. Branaire Ducru 1982 ........ 6th place Wine B is Ch. Cos d'Estournel 1982 ........ 2nd place Wine C is Ch. La Lagune 1982 ........ 3rd place Wine D is Ch. Lalande Borie 1982 ........ 8th place Wine E is Ch. Ducru Beaucaillou 1982 ........ 7th place Wine F is Ch. Grand Ormeau 1982 ........ 1st place Wine G is Ch. Prieure Lichine 1982 ........ 5th place Wine H is Ch. Gruaud Larose 1982 ........ 4th place
The Judges's Rankings
Judge Wine -> A B C D E F G H John 3. 2. 1. 6. 7. 8. 4. 5. Frank 4. 3. 7. 5. 6. 2. 8. 1. Orley 6. 2. 3. 4. 5. 1. 7. 8. Bob L 6. 7. 3. 8. 1. 2. 4. 5. Ed 6. 7. 8. 5. 4. 1. 2. 3. Mike 7. 5. 2. 8. 4. 1. 3. 6. Bob E 6. 4. 5. 1. 8. 7. 2. 3. Dick 1. 2. 4. 7. 5. 6. 8. 3.
Table of Votes Against Wine -> A B C D E F G H
Group Ranking -> 6 2 3 8 7 1 5 4 Votes Against -> 39 32 33 44 40 28 38 34
( 8 is the best possible, 64 is the worst)
Here is a measure of the correlation in the preferences of the judges which ranges between 1.0 (perfect correlation) and 0.0 (no correlation):
W = 0.0692
The probability that random chance could be responsible for this correlation is rather large, 0.7941. Most analysts would say that unless this probability is less than 0.1, the judges' preferences are not strongly related. We now analyze how each taster's preferences are correlated with the group preference. A correlation of 1.0 means that the taster's preferences are a perfect predictor of the group's preferences. A 0.0 means no correlation, while a -1.0 means that the taster has the reverse ranking of the group. This is measured by the correlation R.
Correlation Between the Ranks of Each Person With the Average Ranking of Others
Name of Person Correlation R Mike 0.3856 Orley 0.0838 Frank 0.0359 John -0.1429 Bob L -0.1429 Dick -0.2635 Ed -0.3735 Bob E -0.5389
The wines were preferred by the judges in the following order. When the preferences of the judges are strong enough to permit meaningful differentiation among the wines, they are separated by -------------------- and are judged to be significantly different.
1. ........ 1st place Wine F is Ch. Grand Ormeau 2. ........ 2nd place Wine B is Ch. Cos d'Estournel 1982 3. ........ 3rd place Wine C is Ch. La Lagune 1982 4. ........ 4th place Wine H is Ch. Gruaud Larose 1982 5. ........ 5th place Wine G is Ch. Prieure Lichine 1982 6. ........ 6th place Wine A is Ch. Branaire Ducru 1982 7. ........ 7th place Wine E is Ch. Ducru Beaucaillou 1982 8. ........ 8th place Wine D is Ch. Lalande Borie 1982 We now test whether the ranksums AS A WHOLE provide a significant ordering. The Friedman Chi-square value is 3.8750. The probability that this could happen by chance is 0.7941 We now undertake a more detailed examination of the pair-wise rank correla- tions that exist between pairs of judges. First, we present a table in which you can find the correlation for any pair of judges, by finding one of the names in the left hand margin and the other name on top of a column. A second table arranges these correlations in descending order and marks which is significantly positive significantly negative, or not significant. This may allow you to find clusters of judges whose rankings were particularly similar or particularly dissimilar. Pairwise Rank Correlations Correlations must exceed in absolute value 0.74 for significance at the 0.05 level and must exceed 0.64 for significance at the 0.1 level John Frank Orley John 1.000 -0.286 -0.048 Frank -0.286 1.000 0.119 Orley -0.048 0.119 1.000 Bob L -0.357 -0.214 0.095 Ed -0.786 0.214 -0.214 Mike -0.071 -0.214 0.429 Bob E 0.238 -0.119 -0.333 Dick 0.500 0.476 -0.024 Bob L Ed Mike John -0.357 -0.786 -0.071 Frank -0.214 0.214 -0.214 Orley 0.095 -0.214 0.429 Bob L 1.000 0.381 0.786 Ed 0.381 1.000 0.286 Mike 0.786 0.286 1.000 Bob E -0.714 -0.024 -0.452 Dick -0.238 -0.571 -0.310 Bob E Dick John 0.238 0.500 Frank -0.119 0.476 Orley -0.333 -0.024 Bob L -0.714 -0.238 Ed -0.024 -0.571 Mike -0.452 -0.310 Bob E 1.000 -0.333 Dick -0.333 1.000 Pairwise correlations in descending order 0.786 Bob L and Mike Significantly positive 0.500 John and Dick Not significant 0.476 Frank and Dick Not significant 0.429 Orley and Mike Not significant 0.381 Bob L and Ed Not significant 0.286 Ed and Mike Not significant 0.238 John and Bob E Not significant 0.214 Frank and Ed Not significant 0.119 Frank and Orley Not significant 0.095 Orley and Bob L Not significant -0.024 Orley and Dick Not significant -0.024 Ed and Bob E Not significant -0.048 John and Orley Not significant -0.071 John and Mike Not significant -0.119 Frank and Bob E Not significant -0.214 Orley and Ed Not significant -0.214 Frank and Mike Not significant -0.214 Frank and Bob L Not significant -0.238 Bob L and Dick Not significant -0.286 John and Frank Not significant -0.310 Mike and Dick Not significant -0.333 Bob E and Dick Not significant -0.333 Orley and Bob E Not significant -0.357 John and Bob L Not significant -0.452 Mike and Bob E Not significant -0.571 Ed and Dick Not significant -0.714 Bob L and Bob E Significantly negative -0.786 John and Ed Significantly negative
COMMENT: We are probably the only group that could be drinking Ch. Grand Ormeau 24 years after the vintage. The wines very remarkably similar, which is attested by the very low Kendall W coefficient in the tasting. None of the wines were bad or oxidized and were drinking very well. But it is noteworthy that in spite of Grand Ormeau being the highest ranked wine, none of them was statistically significantly good. 1982, a warm vintage, was often said to have wines that would not last very long. Despite that, all of these wine still retain fruit and were very pleasant to drink. The Merlot Hypothesis: Although this is a limited sample, it is interesting to note that the Merlot won the tasting, indicating that Merlots may age better than the popular conception. Parker came out strongly for 82s and 24 years later his judgment has been vindicated.
Return to previous page